TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Browser-Based LLM Models?

4 点作者 lulzury10 个月前
Does anyone know if there are there any plans for browsers to natively integrate LLMs, LLM APIs, or LLM models like Llama for local use by web applications?<p>I feel there&#x27;s a large opportunity here for a more privacy-friendly, on-device solution that doesn&#x27;t send the user&#x27;s data to OpenAI.<p>Is RAM the current main limitation?

4 条评论

throwaway888abc10 个月前
<a href="https:&#x2F;&#x2F;simonwillison.net&#x2F;2024&#x2F;Jul&#x2F;3&#x2F;chrome-prompt-playground&#x2F;" rel="nofollow">https:&#x2F;&#x2F;simonwillison.net&#x2F;2024&#x2F;Jul&#x2F;3&#x2F;chrome-prompt-playgroun...</a><p><a href="https:&#x2F;&#x2F;developer.chrome.com&#x2F;docs&#x2F;ai&#x2F;built-in" rel="nofollow">https:&#x2F;&#x2F;developer.chrome.com&#x2F;docs&#x2F;ai&#x2F;built-in</a>
评论 #40899099 未加载
throwaway42593310 个月前
Every big tech company is trying to do this. FB (through whatsapp), Google (through chrome&#x2F;Android), Apple (through Safari&#x2F;iOS&#x2F;etc). As soon as they meet their internal metrics, they will release these to public
FrenchDevRemote10 个月前
&quot;Is RAM the current main limitation?&quot;<p>(V)RAM+processing power+storage(I mean what kind of average user wants to clog half their hard drive for a subpar model that output 1 token a second?)
Crier100210 个月前
check out <a href="https:&#x2F;&#x2F;github.com&#x2F;mlc-ai&#x2F;web-llm">https:&#x2F;&#x2F;github.com&#x2F;mlc-ai&#x2F;web-llm</a><p>IMO the main limitation is access to powerful GPUs for running models locally and the size of some models causing UX problems with cold starts